Apple M1 Microarchitecture Research by Dougall Johnson

Firestorm: Overview | Base Instructions | SIMD and FP Instructions
Icestorm:  Overview | Base Instructions | SIMD and FP Instructions

SQSHL (vector, 16B)

Test 1: uops

Code:

  sqshl v0.16b, v0.16b, v1.16b
  movi v0.16b, 1
  movi v1.16b, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)031e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op fp/simd (7e)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst neon or fp (9a)accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150611687251000100010002646800201820372037157231895100010002326203720371110011000073116111787100020382038203820382038
1004203716183611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150821687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037160611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371584611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
10042037160611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  sqshl v0.16b, v0.16b, v1.16b
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03181e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010001807102161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100037101161119791100001002003820038200382003820038
1020420037150030611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100997101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100397391161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037149000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010001477101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
1002420037150066196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000756402162219785110000102003820038200382003820038
100242003715006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000126402162219785010000102003820038200382003820038
10024200371501561196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000126402162219785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000096402162219785010000102003820038200382003820038
10024200371500611968725100101010000101000050285152920018200372003718444318767100102010000202000020037200371110021109101010000100001116402162219785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100001086402162219785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  sqshl v0.16b, v1.16b, v0.16b
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308090b18191e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000000006119687251010012510000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000102043000071031711197910100001002003820038200382003820038
1020420037150000000034619687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000000071011611197910100001002003820038200382003820038
102042003715600000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000000071011611197910100001002003820038200382003820083
102042003715000000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000000071011611197910100001002003820038200382003820038
102042003715000000006119687251010010010000125100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000100000071011611197910100001002003820038200382003820038
102042003715000000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000203000071011611197910100001002003820038200382003820038
102042003715000000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000003000071011611197910100001002003820038200382003820038
102042003715000000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102021009910010010000100000100000071011611197910100001002003820038200382003820038
10204200371500000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002032820227203276110201100991001001000010020210120352000835257122000829100001002032620325203242032220276
10204203231520115067544029701962113610206151100721001106471428553780201982031120279184432718847110502201096022221648203252032371102011009910010010000100402020000083146411197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030408090b18191e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000000064031622197850010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000000064021722197850010000102003820038200382003820038
10024200371500000001206119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000000064021622197850010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680120018200852013118444318767100102010000202000020037200371110021109101010000100000000064021622197850010000102003820038200382003820131
10024200371500000009061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000002000064021622197850010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000002800064021622197850010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000003500064021622197850010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000000064021622197850010000102003820038200382003820038
1002420037150000000906119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000400064021622197850010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000000064021622197850010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  sqshl v0.16b, v8.16b, v9.16b
  sqshl v1.16b, v8.16b, v9.16b
  sqshl v2.16b, v8.16b, v9.16b
  sqshl v3.16b, v8.16b, v9.16b
  sqshl v4.16b, v8.16b, v9.16b
  sqshl v5.16b, v8.16b, v9.16b
  sqshl v6.16b, v8.16b, v9.16b
  sqshl v7.16b, v8.16b, v9.16b
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)03080b18191e1f3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420059150000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511051611200350800001002003920039200392003920039
8020420038150000000822580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
8020420038150000000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
8020420038150000000402580297100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
8020420038150000000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000030511011611200350800001002003920039200392003920039
8020420038150000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
8020420038150000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511013711200350800001002003920039200392003920039
8020420038150000030402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100001430511011611200350800001002003920039200392003920039
8020420038150000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039
8020420038150000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)030b18191e1f3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa1a8acbranch mispredict (cb)cfd5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815000000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010010050201160112003580000102003920039200392003920039
800242003815000000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000050201160112003580000102003920039200392003920039
800242003815000000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010009050201160112003580000102003920039200392003920039
800242003815000000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000050201160112003580000102003920039200392003920039
800242003815000000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000050201160112003580000102003920039200392003920039
800242003815000000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000050201160112003580000102003920039200392003920039
800242003815000000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000050201160112003580000102003920039200392003920039
800242003815000000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000050201160112003580000102003920039200392003920039
800242003815000000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000050201160112003580000102003920039200392003920039
800242003815000000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000050201161112003580000102003920039200392003920039